DeepAI AI Chat
Log In Sign Up

Learning Differentiable Grammars for Continuous Data

by   AJ Piergiovanni, et al.

This paper proposes a novel algorithm which learns a formal regular grammar from real-world continuous data, such as videos or other streaming data. Learning latent terminals, non-terminals, and productions rules directly from streaming data allows the construction of a generative model capturing sequential structures with multiple possibilities. Our model is fully differentiable, and provides easily interpretable results which are important in order to understand the learned structures. It outperforms the state-of-the-art on several challenging datasets and is more accurate for forecasting future activities in videos. We plan to open-source the code.


page 2

page 5

page 6


Unsupervised Discovery of Actions in Instructional Videos

In this paper we address the problem of automatically discovering atomic...

Adversarial Generative Grammars for Human Activity Prediction

In this paper we propose an adversarial generative grammar model for fut...

Neural-based classification rule learning for sequential data

Discovering interpretable patterns for classification of sequential data...

Retracing the Flow of the Stream: Investigating Kodi Streaming Services

Kodi is of one of the world's largest open-source streaming platforms fo...

JSOL: JavaScript Open-source Library for Grammar of Graphics

In this paper, we introduce the JavaScript Open-source Library (), a hig...

Time Perception Machine: Temporal PointProcesses for the When, Where and What ofActivity Prediction

Numerous powerful point process models have been developed to understand...

HyperStream: a Workflow Engine for Streaming Data

This paper describes HyperStream, a large-scale, flexible and robust sof...